Conventional approaches for designing antennas are often time-consuming and computationally expensive processes. In this letter, a time and resource-efficient inverse design method for the multiparameter antenna is pr...
详细信息
Conventional approaches for designing antennas are often time-consuming and computationally expensive processes. In this letter, a time and resource-efficient inverse design method for the multiparameter antenna is proposed which is capable of generating an effective dataset using the hybrid machine learning method. The proposed method filters the design variables and predicts the secondary variables based on the choice of primary design variables. The generated training dataset is used for the effective prediction of design variables based on multiple performance metrics. The proposed machine learning model utilized autoencoder for dimensionality reduction of multiple performance metrics and support vector regression is used for the prediction of design variables. To prove the effectiveness of the proposed model, a metasurface-loaded low-profile antenna is considered as a design example.
We propose an artificial intelligence approach based on deep neural networks to tackle a canonical 2D scalar inverse source problem. The learned singular value decomposition (L-SVD) based on hybrid autoencoding is con...
详细信息
We propose an artificial intelligence approach based on deep neural networks to tackle a canonical 2D scalar inverse source problem. The learned singular value decomposition (L-SVD) based on hybrid autoencoding is considered. We compare the reconstruction performance of L-SVD to the Truncated SVD (TSVD) regularized inversion, which is a canonical regularization scheme, to solve an ill-posed linear inverse problem. Numerical tests referring to far-field acquisitions show that L-SVD provides, with proper training on a well-organized dataset, superior performance in terms of reconstruction errors as compared to TSVD, allowing for the retrieval of faster spatial variations of the source. Indeed, L-SVD accommodates a priori information on the set of relevant unknown current distributions. Different from TSVD, which performs linear processing on a linear problem, L-SVD operates non-linearly on the data. A numerical analysis also underlines how the performance of the L-SVD degrades when the unknown source does not match the training dataset.
Stress testing refers to the application of adverse financial or macroeconomic scenarios to a portfolio. For this purpose, financial or macroeconomic risk factors are linked with asset returns, typically via a factor ...
详细信息
Stress testing refers to the application of adverse financial or macroeconomic scenarios to a portfolio. For this purpose, financial or macroeconomic risk factors are linked with asset returns, typically via a factor model. We expand the range of risk factors by adapting dimension-reduction techniques from unsupervised learning, namely PCA and autoencoders. This results in aggregated risk factors, encompassing a global factor, factors representing broad geographical regions, and factors specific to cyclical and defensive industries. As the adapted PCA and autoencoders provide an interpretation of the latent factors, this methodology is also valuable in other areas where dimension-reduction and explainability are critical.
With the rapid development of modern military countermeasure technology, deep distinguish hostile radar is essential in electronic warfare. However, traditional radio frequency (RF) feature extraction methods can easi...
详细信息
With the rapid development of modern military countermeasure technology, deep distinguish hostile radar is essential in electronic warfare. However, traditional radio frequency (RF) feature extraction methods can easily be interfered by signal information and fail due to the lack of research on RF feature extraction techniques for complex situations. Therefore, in this paper, first, the generation mechanism of RF structure information is discussed, and the influence of different signal information introduced by different operating parameters on RF structure feature extraction is analyzed. Then, an autoencoder (AE) network and an autoencoder metric (AEM) network are designed, introducing metric learning ideas, so that the extracted deep RF structure features have good stability and divisibility. Finally, radar emitter structure (RES) inversion is realized using the centroid-matching method. The experimental results demonstrate that this method exhibits good inversion performance under variable operating parameters (modulation type, frequency, bandwidth, input power). RES inversion including unknown operating parameters is realized for the first time, and it is shown that metric learning has the advantage of separability of RF feature extraction, which can provide an idea in emitter and RF feature extraction.
Positioning service is a critical technology that bridges the physical world with digital information, significantly enhancing efficiency and convenience in life and work. The evolution of 5G technology has proven tha...
详细信息
Positioning service is a critical technology that bridges the physical world with digital information, significantly enhancing efficiency and convenience in life and work. The evolution of 5G technology has proven that positioning services are integral components of current and future cellular networks. However, positioning accuracy is hindered by non-line-of-sight (NLoS) propagation, which severely affects the measurements of angles and delays. In this study, we introduced a deep autoencoding channel transform-generative adversarial network model that utilizes line-of-sight (LoS) samples as a singular category training set to fully extract the latent features of LoS, ultimately employing a discriminator as an NLoS identifier. We validated the proposed model in 5G indoor and indoor factory (dense clutter, low base station) scenarios by assessing its generalization capability across different scenarios. The results indicate that, compared to the state-of-the-art method, the proposed model markedly diminished the utilization of device resources and achieved a 2.15% higher area under the curve while reducing computing time by 12.6%. This approach holds promise for deployment in future positioning terminals to achieve superior localization precision, catering to commercial and industrial Internet of Things applications.
Although hydraulic accumulators play a vital role in the hydraulic system, they face the challenges of being broken by continuous abnormal pulsating pressure which occurs due to the malfunction of hydraulic systems. H...
详细信息
Although hydraulic accumulators play a vital role in the hydraulic system, they face the challenges of being broken by continuous abnormal pulsating pressure which occurs due to the malfunction of hydraulic systems. Hence, this study develops anomaly detection algorithms to detect abnormalities of pulsating pressure for hydraulic accumulators. A digital pressure sensor was installed in a hydraulic accumulator to acquire the pulsating pressure data. Six anomaly detection algorithms were developed based on the acquired data. A threshold averaging algorithm over a period based on the averaged maximum/minimum thresholds detected anomalies 2.5 h before the hydraulic accumulator failure. In the support vector machine (SVM) and XGBoost model that distinguish normal and abnormal pulsating pressure data, the SVM model had an accuracy of 0.8571 on the test set and the XGBoost model had an accuracy of 0.8857. In a convolutional neural network (CNN) and CNN autoencoder model trained with normal and abnormal pulsating pressure images, the CNN model had an accuracy of 0.9714, and the CNN autoencoder model correctly detected the 8 abnormal images out of 11 abnormal images. The long short-term memory (LSTM) autoencoder model detected 36 abnormal data points in the test set.
In this study, we focus on the challenge of robot motion generation, which is critical for improving the ability of robots to perform downstream tasks. To this end, inspired by the idea of variational inference, we pr...
详细信息
In this study, we focus on the challenge of robot motion generation, which is critical for improving the ability of robots to perform downstream tasks. To this end, inspired by the idea of variational inference, we propose a novel teacher-student hierarchical approach for learning continuous primitive spaces to generate robot motions. We first learn a variational auto-encoder (VAE) based on Gated Recurrent Unit (GRU) from demonstrations, the encoder is used as a teacher model to encode trajectories to primitive information, and the decoder aims to decode latent information to joint trajectories. To learn a primitive action space for the high-level model, we propose a novel learning method to train a student model. We utilize the trained teacher to encode trajectories to labels, and use the Kullback-Leibler (KL) divergence and the reconstruction errors between the label and the predicted primitive information as the loss to train a student model. We then utilize trained student models to guide high-level policy learning. We evaluate our approach on three different robot datasets. Experiments demonstrate that our method obtains the ability to generate new motion and discover common information across tasks, it also can be used to accelerate downstream task learning.
With the rapid development of deep learning methods, the data-driven approach has shown powerful advantages over the model-driven one. In this paper, we propose an end-to-end autoencoder communication system based on ...
详细信息
With the rapid development of deep learning methods, the data-driven approach has shown powerful advantages over the model-driven one. In this paper, we propose an end-to-end autoencoder communication system based on Deep Residual Shrinkage Networks (DRSNs), where neural networks (DNNs) are used to implement the coding, decoding, modulation and demodulation functions of the communication system. Our proposed autoencoder communication system can better reduce the signal noise by adding an “attention mechanism” and “soft thresholding” modules and has better performance at various signal-to-noise ratios (SNR). Also, we have shown through comparative experiments that the system can operate at moderate block lengths and support different throughputs. It has been shown to work efficiently in the AWGN channel. Simulation results show that our model has a higher Bit-Error-Rate (BER) gain and greatly improved decoding performance compared to conventional modulation and classical autoencoder systems at various signal-to-noise ratios.
In this paper,we propose a intrusion detection algorithm based on auto-encoder and three-way decisions(AE-3WD)for industrial control networks,aiming at the security problem of industrial control *** ideology of deep l...
详细信息
In this paper,we propose a intrusion detection algorithm based on auto-encoder and three-way decisions(AE-3WD)for industrial control networks,aiming at the security problem of industrial control *** ideology of deep learning is similar to the idea of intrusion *** learning is a kind of intelligent algorithm and has the ability of automatically *** uses self-learning to enhance the experience and dynamic classification *** use deep learning to improve the intrusion detection rate and reduce the false alarm rate through learning,a denoising autoencoder and three-way decisions intrusion detection method AE-3WD is proposed to improve intrusion detection *** the processing,deep learning autoencoder is used to extract the features of high-dimensional data by combining the coefficient penalty and reconstruction loss function of the encode layer during the training mode.A multi-feature space can be constructed by multiple feature extractions from autoencoder,and then a decision for intrusion behavior or normal behavior is made by three-way ***-KDD data sets are used to the *** experiment results prove that our proposed method can extract meaningful features and effectively improve the performance of intrusion detection.
This paper introduces and applies the Scalable Data-based Diagnostic Concept. At its core, the concept consists of (Kernel) Principal Component Analysis (PCA) and autoencoder (AE), which are used to perform accurate f...
详细信息
This paper introduces and applies the Scalable Data-based Diagnostic Concept. At its core, the concept consists of (Kernel) Principal Component Analysis (PCA) and autoencoder (AE), which are used to perform accurate fault diagnosis in technical systems, e.g. in automotive or railroad sectors, including various sub-methods for fault detection, identification and isolation. The analysis of real automotive fault cases is done, where a new smoothed comparative detection chart is presented. The findings prove the necessity of choosing the right method, regarding efficiency and the inherent data structure, which is one of the main objectives of the comprehensive scalable diagnostic concept.
暂无评论